© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 25813
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'seminar'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.17
    0.9%
    108
    +0.15
    0.8%
    181
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.17
    0.01
    108
    +0.15
    0.01
    479
    +0.14
    0.01
    Negative Logits
    ĥ½
    -2.82
    ľ
    -2.31
    ı
    -2.26
    Ĥ¬
    -2.20
    ħ
    -2.08
    Īĺ
    -2.07
    Ń
    -2.05
    ĥ
    -2.01
    §
    -2.00
    »
    -1.98
    POSITIVE LOGITS
    ist
    1.86
    atus
    1.79
    antry
    1.78
    nor
    1.73
    nier
    1.68
    agraph
    1.67
    asek
    1.65
    face
    1.65
    ue
    1.59
    amble
    1.59
    Activations Density 0.013%

    No Known Activations